Research

On Research

I am marching towards Synergetic & Holistic Intelligence.

My long term goal is to advance AI research and technologies in interrelated fields such as computer vision, machine learning, language understanding and robotics, to build intelligent systems, either virtual or embodied, to facilitate understanding multiple sensory inputs, to gain actionable insights from perception to cognition, to solve important real-world problems and to better serve our human race.

In the medium term, I am putting more emphasis on computer vision, machine learning and their applications, with a strong focus on accurate & efficient understanding of various types of objects and activities from sensory inputs such as images and videos. Over the past few years, I have explored a wide range of topics towards accurate visual understanding: from image-level classification, to instance-level object detection, to video-level detection and tracking, and more recently to spatio-temporal activity recognition. My team and I have been lucky to have won some international AI competitions and set new state-of-the-arts on major computer vision benchmarks. I am also fortunate to have been working on a broad spectrum of applied research projects, from research assistant, to team leader, and PI/Co-PI, with collaborators from industry, academic units and government agencies. This enables me to understand the true depth of challenges arose from real-world data and problems, or even in collaboration, management and technology transfer.

To emphasize, my current research focuses on accurate & efficient visual understanding for intelligent systems, in particular I have recently worked in:

    • Computer Vision: classification, object detection, segmentation, activity recognition
    • Machine Learning: weakly-supervised learning, transfer learning, multi-task learning
    • AI Systems & Applications for Science, Education, Agriculture, Medcine, Finance, Transportation, etc.

My research activities include multiple aspects to solve such problems and to advance AI research: projects, papers, competitions, etc.

Research Highlights

Please find more publication and technical reports on Google Scholar.

Abbreviations: [C]: Conference; [J] Journal; [W] Workshop; [TR]: Technical Report; [B]: Book; [P]: Patent; [Comp]: Competition; [Proj]: Project; [SOTA]: State-of-the-art (at the time of publication)

Classification:

Object Detection:

Segmentation:

Activity Recognition:

    • [Proj] Deep Intermodal Video Analytics (DIVA), sponsored by IARPA, 2017.10 - 2021.09
    • [W] Object-Centric Spatio-Temporal Activity Detection and Recognition, Mandis Beigi, Lisa M Brown, Quanfu Fan, John Henning, Chung-Ching Lin, Honghui Shi, Chiao-fe Shu, Rogerio Feris, NIST TRECVID Workshop, 2018
    • [Comp] NIST/IARPA TRECVID Activity Recognition Challenge 1st Place (2018)

AI Systems & Applications:

    • [Comp] IEEE DAC System Design Contest 1st Place (2019)
    • [Proj] AI for Education, sponsored by New Oriental Education Technology
    • [Proj] Deep Pattern Analysis in Agricultural Images, sponsored by IntelinAir
    • [Proj] Multiphoton Image Analysis for Cancer Diagnosis, sponsored by Mayo Clinic & UIUC
    • [Proj] Intelligent Learning Advisor, sponsored by IBM Research
    • [Proj] Multi-modal Medical Image Understanding, sponsored by Jump ARCHES
    • [Proj] Deep Learning in Financial Modeling and Strategy, sponsored by Jump Trading
    • [Proj] Galaxy Classification and Gravitational Lens Detection, collaborated with UIUC Astronomy